Discover the latest trends and best practices impacting data-intensive applications. Register for access to all 60+ sessions available on demand.
Pinterest relies on Apache Flink to power revenue-critical use cases like real-time ad metrics and budget calculations at global scale, but building stateful streaming applications with low latency and high throughput across petabytes of data is genuinely hard. This talk shares practical lessons and hard-won insights for scaling Flink applications to meet internet-scale demands.
Sanchay Javeria is a Senior Software Engineer at Pinterest, where he leads the Ads data infrastructure that powers the Pinterest Ads Manager. He has architected and built solutions that process several petabytes of data daily, overseeing the entire stack, including compute, data storage, table and file formats, and query systems.
Zach Mullins is a Senior Software Engineer at Pinterest, where he works on the Ads Reporting stack. His work includes creating services and optimizing the queries that power Pinterest Ads Manager and Reporting APIs, by efficiently aggregate large volumes of data in both Druid and Starrocks.
